Detecting tactical patterns in basketball: Comparison of merge self-organising maps and dynamic controlled neural networks

作者：Kempe Matthias^*; Grunz Andreas; Memmert Daniel

来源：European Journal of Sport Science, 2015, 15(4): 249-255.

DOI：10.1080/17461391.2014.933882

• pattern recognition
• Neuronal networks
• performance analysis
• basketball

The soaring amount of data, especially spatial-temporal data, recorded in recent years demands for advanced analysis methods. Neural networks derived from self-organizing maps established themselves as a useful tool to analyse static and temporal data. In this study, we applied the merge self-organising map (MSOM) to spatio-temporal data. To do so, we investigated the ability of MSOM ' s to analyse spatio-temporal data and compared its performance to the common dynamical controlled network (DyCoN) approach to analyse team sport position data. The position data of 10 players were recorded via the Ubisense tracking system during a basketball game. Furthermore, three different pre-selected plays were recorded for classification. Following data preparation, the different nets were trained with the data of the first half. The training success of both networks was evaluated by achieved entropy. The second half of the basketball game was presented to both nets for automatic classification. Both approaches were able to present the trained data extremely well and to detect the pre-selected plays correctly. In conclusion, MSOMs are a useful tool to analyse spatial-temporal data, especially in team sports. By their direct inclusion of different time length of tactical patterns, they open up new opportunities within team sports.

• 出版日期2015-5-19